Investigations on Driver Unique Identification from Smartphone’s GPS Data Alone

<table class="fixed-width table-group" id="tab2"><tr><td><table class="table"><colgroup><col style="width:33.61em"/><col style="width:23.57em"/></colgroup><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td class="align_left">Data</td><td class="align_center">Feature</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">Speed, jerk, jerk energy, lateral acceleration, angular speed, and longitudinal acceleration</td><td class="align_center" rowspan="3">Mean, median, skewness, kurtosis, standard deviation, max, min, 97.5th percentile, 1st and 3rd quartiles (Q1, Q3), IQR (interquartile range: Q3–Q1), and 2.5th percentile</td></tr><tr><td class="align_left">Positive lateral acceleration, negative longitudinal acceleration, positive lateral acceleration, and negative longitudinal acceleration</td></tr><tr><td class="align_left">All 1st and 2nd derivatives of data in rows 1 and 2</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Summary of features for driver identification.</div>

Journal of Advanced Transportation

tab2

Table 2

Table 2: Investigations on Driver Unique Identification from Smartphone’s GPS Data Alone 